UFC Fight Night: Barboza vs. Lee: Predictions & Analysis
UFC Fight Night: Barboza vs. Lee lands on Saturday, April 21, 2018 in Atlantic City, New Jersey, USA with 11 bouts on the card. The card is headlined by a championship fight. Below is our fight-by-fight breakdown, combining Elo ratings, rolling statistical trends, style matchup data, and betting market context into a pick for every bout.
Quick Picks
| Matchup | Pick | Confidence | Prob |
|---|---|---|---|
| Kevin Lee vs Edson BarbozaLightweight | Kevin Lee | Confident | 71% |
| Frankie Edgar vs Cub SwansonFeatherweight | Frankie Edgar | Confident | 69% |
| Justin Willis vs Chase ShermanHeavyweight | Justin Willis | Confident | 74% |
| David Branch vs Thiago SantosMiddleweight | Thiago Santos | Lean | 55% |
| Aljamain Sterling vs Brett JohnsBantamweight | Aljamain Sterling | Toss-up | 51% |
| Dan Hooker vs Jim MillerLightweight | Dan Hooker | Lean | 58% |
| Ryan LaFlare vs Alex GarciaWelterweight | Alex Garcia | Toss-up | 52% |
| Ricky Simon vs Merab DvalishviliBantamweight | Ricky Simon | Lean | 56% |
| Siyar Bahadurzada vs Luan ChagasWelterweight | Luan Chagas | Lean | 57% |
| Corey Anderson vs Patrick CumminsLight Heavyweight | Corey Anderson | Confident | 70% |
| Anthony Rocco Martin vs Keita NakamuraWelterweight | Anthony Rocco Martin | Lean | 60% |
Fight-by-Fight Breakdown
Kevin Lee vs Edson Barboza
The Lightweight championship matchup features Kevin Lee (11-7) taking on Edson Barboza (18-13).
Lee carries a modest Elo edge (1197 to 1142), the kind of gap that reflects a slightly better run of form rather than a talent chasm.
Stylistically this is Lee's wrestler game against Barboza's striker approach. Lee looks to close distance and put the fight on the mat, while Barboza brings a versatile approach. Historically these archetypes are dead-even when they collide.
A few statistical edges stand out. Barboza throws significantly more leather — a 0.3 sig. strike per minute gap. Lee is far more active with takedowns, averaging 4.1 more per 15 minutes. Barboza has tighter striking defense, making opponents miss more often.
**The Pick: Kevin Lee over Edson Barboza.** We're leaning Lee here at 71%, a solid but not overwhelming edge. Notably, the betting market has Lee at 60% implied while our model sees 71% — a 11-point disagreement that could signal value.
Frankie Edgar vs Cub Swanson
The Featherweight matchup features Frankie Edgar (18-10-1) taking on Cub Swanson (14-10). Swanson is the bigger frame at 5'8" with a 2-inch reach advantage.
Swanson carries a modest Elo edge (1255 to 1185), the kind of gap that reflects a slightly better run of form rather than a talent chasm.
Both fighters land in our "All-Rounder" archetype — fighters comfortable everywhere, able to strike or grapple depending on what the opponent gives them. When mirror matchups like this happen, the edge usually goes to whoever can impose their preferred pace and range.
A few statistical edges stand out. Swanson throws significantly more leather — a 2.7 sig. strike per minute gap. Edgar is far more active with takedowns, averaging 0.6 more per 15 minutes. Edgar has tighter striking defense, making opponents miss more often.
**The Pick: Frankie Edgar over Cub Swanson.** We're leaning Edgar here at 69%, a solid but not overwhelming edge. The market implies 72% for Edgar, but our model sees only 69%. That 4-point gap favoring Swanson is worth watching.
Justin Willis vs Chase Sherman
The Heavyweight matchup features Justin Willis (4-0) taking on Chase Sherman (4-10). There's a 3-inch height gap favoring Sherman.
Willis is rated at 1256 — 433 points above Sherman's 822. Gaps this large usually mean one fighter has been consistently beating better opponents. Willis rides a 4-fight win streak into this one.
A few statistical edges stand out. Sherman throws significantly more leather — a 2.0 sig. strike per minute gap. Willis is far more active with takedowns, averaging 2.6 more per 15 minutes. Willis has tighter striking defense, making opponents miss more often.
**The Pick: Justin Willis over Chase Sherman.** We're leaning Willis here at 74%, a solid but not overwhelming edge. The market and our model are aligned — the line looks fair.
David Branch vs Thiago Santos
The Middleweight matchup features David Branch (4-4) taking on Thiago Santos (14-9).
Santos is rated at 1292 — 156 points above Branch's 1136. Gaps this large usually mean one fighter has been consistently beating better opponents.
Both fighters land in our "Striker" archetype — fighters with a well-rounded skill set. When mirror matchups like this happen, the edge usually goes to whoever can impose their preferred pace and range.
A few statistical edges stand out. Santos throws significantly more leather — a 4.5 sig. strike per minute gap. Branch is far more active with takedowns, averaging 2.2 more per 15 minutes. Santos has tighter striking defense, making opponents miss more often.
**The Pick: Thiago Santos over David Branch.** The model gives Santos a slight nod at 55% — this could easily go either way. Notably, the betting market has Branch at 39% implied while our model sees 45% — a 5-point disagreement that could signal value.
Aljamain Sterling vs Brett Johns
The Bantamweight matchup features Aljamain Sterling (16-5) taking on Brett Johns (4-2).
Sterling is rated at 1683 — 388 points above Johns's 1295. Gaps this large usually mean one fighter has been consistently beating better opponents.
The style clash matters here: Sterling is comfortable adjusting on the fly, mixing strikes and grappling as openings appear, while Johns looks to close distance and put the fight on the mat. In our database, wrestlers own a 59% win rate against all-rounders, giving Johns the stylistic edge.
A few statistical edges stand out. Sterling throws significantly more leather — a 0.5 sig. strike per minute gap. Johns is far more active with takedowns, averaging 5.9 more per 15 minutes. Sterling has tighter striking defense, making opponents miss more often.
**The Pick: Aljamain Sterling over Brett Johns.** This is essentially a pick'em. The model nudges toward Sterling at 51%, but there's almost nothing separating these two. The market and our model are aligned — the line looks fair.
Dan Hooker vs Jim Miller
The Lightweight matchup features Dan Hooker (14-9) taking on Jim Miller (27-17). Hooker is the bigger frame at 6'0" with a 4-inch reach advantage.
Hooker is rated at 1450 — 237 points above Miller's 1213. Gaps this large usually mean one fighter has been consistently beating better opponents.
Both fighters land in our "All-Rounder" archetype — fighters comfortable everywhere, able to strike or grapple depending on what the opponent gives them. When mirror matchups like this happen, the edge usually goes to whoever can impose their preferred pace and range.
A few statistical edges stand out. Miller throws significantly more leather — a 0.3 sig. strike per minute gap. Miller is far more active with takedowns, averaging 0.5 more per 15 minutes. Hooker has tighter striking defense, making opponents miss more often.
**The Pick: Dan Hooker over Jim Miller.** The model gives Hooker a slight nod at 58% — this could easily go either way.
Ryan LaFlare vs Alex Garcia
The Welterweight matchup features Ryan LaFlare (7-2) taking on Alex Garcia (5-4). LaFlare is the bigger frame at 6'1" with a 2-inch reach advantage.
LaFlare is rated at 1174 — 167 points above Garcia's 1006. Gaps this large usually mean one fighter has been consistently beating better opponents.
Stylistically this is LaFlare's striker game against Garcia's wrestler approach. LaFlare brings a versatile approach, while Garcia looks to close distance and put the fight on the mat. Historically these archetypes are dead-even when they collide.
A few statistical edges stand out. LaFlare throws significantly more leather — a 0.7 sig. strike per minute gap. Garcia is far more active with takedowns, averaging 2.2 more per 15 minutes. Garcia has tighter striking defense, making opponents miss more often.
**The Pick: Alex Garcia over Ryan LaFlare.** This is essentially a pick'em. The model nudges toward Garcia at 52%, but there's almost nothing separating these two. The market implies 58% for LaFlare, but our model sees only 48%. That 10-point gap favoring Garcia is worth watching.
Ricky Simon vs Merab Dvalishvili
The Bantamweight matchup features Ricky Simon (10-5) taking on Merab Dvalishvili (14-2).
Dvalishvili is rated at 1867 — 643 points above Simon's 1223. Gaps this large usually mean one fighter has been consistently beating better opponents. Dvalishvili has won 14 straight.
The style clash matters here: Simon is comfortable adjusting on the fly, mixing strikes and grappling as openings appear, while Dvalishvili looks to close distance and put the fight on the mat. In our database, wrestlers own a 59% win rate against all-rounders, giving Dvalishvili the stylistic edge.
A few statistical edges stand out. Dvalishvili throws significantly more leather — a 3.1 sig. strike per minute gap. Dvalishvili is far more active with takedowns, averaging 11.0 more per 15 minutes. Simon has tighter striking defense, making opponents miss more often.
**The Pick: Ricky Simon over Merab Dvalishvili.** The model gives Simon a slight nod at 56% — this could easily go either way. The market and our model are aligned — the line looks fair.
Siyar Bahadurzada vs Luan Chagas
The Welterweight matchup features Siyar Bahadurzada (4-3) taking on Luan Chagas (1-1-1).
There's a real Elo separation here: Bahadurzada at 1086 versus Chagas at 973. That 113-point gap typically reflects a meaningful difference in recent quality of competition and results.
A few statistical edges stand out. Chagas throws significantly more leather — a 1.3 sig. strike per minute gap. Bahadurzada is far more active with takedowns, averaging 0.7 more per 15 minutes. Chagas has tighter striking defense, making opponents miss more often.
**The Pick: Luan Chagas over Siyar Bahadurzada.** The model gives Chagas a slight nod at 57% — this could easily go either way. Notably, the betting market has Bahadurzada at 40% implied while our model sees 43% — a 3-point disagreement that could signal value.
Corey Anderson vs Patrick Cummins
The Light Heavyweight matchup features Corey Anderson (10-4) taking on Patrick Cummins (6-6). Anderson will look to use a 3-inch reach edge to control distance.
Anderson is rated at 1459 — 592 points above Cummins's 867. Gaps this large usually mean one fighter has been consistently beating better opponents. Anderson rides a 4-fight win streak into this one.
Both fighters land in our "Striker" archetype — fighters with a well-rounded skill set. When mirror matchups like this happen, the edge usually goes to whoever can impose their preferred pace and range.
A few statistical edges stand out. Cummins throws significantly more leather — a 0.8 sig. strike per minute gap. Cummins is far more active with takedowns, averaging 0.6 more per 15 minutes. Anderson has tighter striking defense, making opponents miss more often.
**The Pick: Corey Anderson over Patrick Cummins.** We're leaning Anderson here at 70%, a solid but not overwhelming edge. Notably, the betting market has Anderson at 58% implied while our model sees 70% — a 12-point disagreement that could signal value.
Anthony Rocco Martin vs Keita Nakamura
The Welterweight matchup features Anthony Rocco Martin (9-5) taking on Keita Nakamura (4-6).
Martin is rated at 1419 — 433 points above Nakamura's 987. Gaps this large usually mean one fighter has been consistently beating better opponents.
Both fighters land in our "Wrestler" archetype — fighters who win by dictating where the fight takes place, grinding out control time and wearing opponents down. When mirror matchups like this happen, the edge usually goes to whoever can impose their preferred pace and range.
A few statistical edges stand out. Martin throws significantly more leather — a 0.9 sig. strike per minute gap. Nakamura is far more active with takedowns, averaging 1.1 more per 15 minutes. Martin has tighter striking defense, making opponents miss more often.
**The Pick: Anthony Rocco Martin over Keita Nakamura.** The model gives Martin a slight nod at 60% — this could easily go either way.
Methodology
Predictions are generated by our ensemble model combining LightGBM (65%) and CatBoost (35%), trained on every UFC fight since 1994. The model uses 23 features including Elo ratings, rolling 5-fight statistical averages, style matchup history, physical attributes, and market odds when available.
On our held-out test set (402 fights from January-September 2023), the model achieves 63.4% accuracy with a log-loss of 0.626. High-confidence picks (>75% probability) hit at 82.7%. For full model transparency, visit our Model page.